Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2895 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2916. Min Range: -6.2916
Max Act: 6.2916. Min Act: -0.1700
Data Index: 6415434 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2916. Min Range: -6.2916
Max Act: 6.1041. Min Act: -0.1700
Data Index: 3136832 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.9479. Min Act: -0.1700
Data Index: 6966072 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.9166. Min Act: -0.1700
Data Index: 8578587 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.8854. Min Act: -0.1700
Data Index: 3215692 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.8854. Min Act: -0.1700
Data Index: 94232 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.8229. Min Act: -0.1700
Data Index: 1222741 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.8229. Min Act: -0.1700
Data Index: 5391016 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.8229. Min Act: -0.1700
Data Index: 1030915 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.7604. Min Act: -0.1700
Data Index: 1704905 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.7604. Min Act: -0.1700
Data Index: 4352744 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.7291. Min Act: -0.1700
Data Index: 1447136 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.7291. Min Act: -0.1700
Data Index: 755857 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.7291. Min Act: -0.1700
Data Index: 3988586 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.6979. Min Act: -0.1700
Data Index: 7131813 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.6979. Min Act: -0.1700
Data Index: 8113131 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.6979. Min Act: -0.1700
Data Index: 1891169 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.6666. Min Act: -0.1700
Data Index: 2293336 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.6979. Min Act: -0.1700
Data Index: 6026934 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2916. Min Range: -6.2916
Max Act: 5.6354. Min Act: -0.1700
Data Index: 4933333 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19